Revealing power, energy and thermal dynamics of a 200PF pre-exascale supercomputer
Woong Shin, Vladyslav Oles, Ahmad Maroof Karimi, J. Austin Ellis, Feiyi Wang
摘要
As we approach the exascale computing era, the focused understanding of power consumption and its overall constraint on HPC architectures and applications are becoming increasingly paramount. Summit, located at the Oak Ridge Leadership Computing Facility (OLCF), is one of the fastest and largest pre-exascale platforms in operation today. This paper provides a first-order examination and analysis of power consumption at the component-level, node-level, and system-level, from all 4,626 Summit compute nodes, each with over 100 metrics at 1Hz frequency over the entire year of 2020. We also investigate the power characteristics and energy efficiency of over 840k Summit jobs and 250k GPU failure logs for further operational insights. To the best of our knowledge, this is the first systematic analysis of power data of HPC system at this scale.
• General and reference → General conference proceedings;
• Hardware → Enterprise level and data centers power issues.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference ServiceBaolin Li, Siddharth Samsi, Vijay Gadepally, Devesh TiwariSC 2023 · 被引用 63 次
- A Digital Twin Framework for Liquid-cooled Supercomputers as Demonstrated at ExascaleWesley Brewer, Matthias Maiterth, Vineet Kumar, Rafal P. Wojda 等SC 2024 · 被引用 22 次
- Towards Scalable Resource Management for SupercomputersYiqin Dai, Yong Dong, Kai Lu, Ruibo Wang 等SC 2022 · 被引用 12 次
- ThirstyFLOPS: Water Footprint Modeling and Analysis Toward Sustainable HPC SystemsYankai Jiang, Raghavendra Kanakagiri, Rohan Basu Roy, Devesh TiwariSC 2025 · 被引用 4 次
它引用的顶会 Paper2
- Job characteristics on large-scale systems: long-term analysis, quantification, and implicationsTirthak Patel, Zhengchun Liu, Raj Kettimuthu, Paul Rich 等SC 2020 · 被引用 48 次
- GPU lifetimes on titan supercomputer: survival analysis and reliabilityGeorge Ostrouchov, Don Maxwell, Rizwan A. Ashraf, Christian Engelmann 等SC 2020 · 被引用 38 次
相关 Paper
- Experiences readying applications for ExascaleNicholas Malaya, Bronson Messer, Joseph Glenski, Antigoni Georgiadou 等SC 2023 · 被引用 9 次
- Not All GPUs Are Created Equal: Characterizing Variability in Large-Scale, Accelerator-Rich SystemsPrasoon Sinha, Akhil Guliani, Rutwik Jain, Brandon Tran 等SC 2022 · 被引用 31 次
- Frontier: Exploring ExascaleScott Atchley, Christopher Zimmer, John Lange, David E. Bernholdt 等SC 2023 · 被引用 91 次
- Climbing the Summit and Pushing the Frontier of Mixed Precision Benchmarks at Extreme ScaleHao Lu, Michael A. Matheson, Vladyslav Oles, J. Austin Ellis 等SC 2022 · 被引用 8 次
- DCDB Wintermute: Enabling Online and Holistic Operational Data Analytics on HPC SystemsAlessio Netti, Micha Müller, Carla Guillén, Michael Ott 等HPDC 2020 · 被引用 35 次
